1 / 35

Keypoint extraction: Corners

Keypoint extraction: Corners. 9300 Harris Corners Pkwy, Charlotte, NC. Why extract keypoints ?. Motivation: panorama stitching We have two images – how do we combine them?. Step 2: match keypoint features. Why extract keypoints ?. Motivation: panorama stitching

Albert_Lan
Download Presentation

Keypoint extraction: Corners

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Keypoint extraction: Corners 9300 Harris Corners Pkwy, Charlotte, NC

  2. Why extract keypoints? • Motivation: panorama stitching • We have two images – how do we combine them?

  3. Step 2: match keypoint features Why extract keypoints? • Motivation: panorama stitching • We have two images – how do we combine them? Step 1: extract keypoints

  4. Why extract keypoints? • Motivation: panorama stitching • We have two images – how do we combine them? Step 1: extract keypoints Step 2: match keypoint features Step 3: align images

  5. Characteristics of good keypoints • Compactness and efficiency • Many fewer keypoints than image pixels • Saliency • Each keypoint is distinctive • Locality • A keypoint occupies a relatively small area of the image; robust to clutter and occlusion • Repeatability • The same keypoint can be found in several images despite geometric and photometric transformations

  6. Applications • Keypoints are used for: • Image alignment • 3D reconstruction • Motion tracking • Robot navigation • Database indexing and retrieval • Object recognition

  7. Corner detection: Basic idea

  8. “flat” region:no change in all directions “edge”:no change along the edge direction “corner”:significant change in all directions Corner detection: Basic idea • We should easily recognize the point by looking through a small window • Shifting a window in anydirection should give a large change in intensity

  9. Corner Detection: Derivation Change in appearance of window W for the shift [u,v]: I(x, y) E(u, v) E(3,2)

  10. Corner Detection: Derivation Change in appearance of window W for the shift [u,v]: I(x, y) E(u, v) E(0,0)

  11. Corner Detection: Derivation Change in appearance of window W for the shift [u,v]: We want to find out how this function behaves for small shifts E(u, v)

  12. Corner Detection: Derivation • First-order Taylor approximation for small motions [u, v]: • Let’s plug this into E(u,v):

  13. Corner Detection: Derivation • E(u,v) can be locally approximated by a quadratic surface: • In which directions does this surface have the fastest/slowest change? E(u, v)

  14. Corner Detection: Derivation • E(u,v) can be locally approximated by a quadratic surface: Second moment matrixM

  15. Interpreting the second moment matrix A horizontal “slice” of E(u, v) is given by the equation of an ellipse:

  16. Interpreting the second moment matrix Consider the axis-aligned case (gradients are either horizontal or vertical): a-1/2 Minor axis Major axis b-1/2

  17. Interpreting the second moment matrix Consider the axis-aligned case (gradients are either horizontal or vertical): If either a or b is close to 0, then this is not a corner, so we want locations where both are large

  18. direction of the fastest change direction of the slowest change (max)-1/2 (min)-1/2 Interpreting the second moment matrix In the general case, need to diagonalize M: The axis lengths of the ellipse are determined by the eigenvalues and the orientation is determined by R:

  19. Visualization of second moment matrices

  20. Visualization of second moment matrices

  21. Interpreting the eigenvalues Classification of image points using eigenvalues of M: 2 “Edge” 2 >> 1 “Corner”1 and 2 are large,1 ~ 2;E increases in all directions 1 and 2 are small;E is almost constant in all directions “Edge” 1 >> 2 “Flat” region 1

  22. Corner response function α: constant (0.04 to 0.06) “Edge” R < 0 “Corner”R > 0 |R| small “Edge” R < 0 “Flat” region

  23. The Harris corner detector • Compute partial derivatives at each pixel • Compute second moment matrix M in a Gaussian window around each pixel: C.Harris and M.Stephens, A Combined Corner and Edge Detector, Proceedings of the 4th Alvey Vision Conference: pages 147—151, 1988. 

  24. The Harris corner detector • Compute partial derivatives at each pixel • Compute second moment matrix M in a Gaussian window around each pixel • Compute corner response function R C.Harris and M.Stephens, A Combined Corner and Edge Detector, Proceedings of the 4th Alvey Vision Conference: pages 147—151, 1988. 

  25. Harris Detector: Steps

  26. Harris Detector: Steps Compute corner response R

  27. The Harris corner detector • Compute partial derivatives at each pixel • Compute second moment matrix M in a Gaussian window around each pixel • Compute corner response function R • Threshold R • Find local maxima of response function (nonmaximum suppression) C.Harris and M.Stephens, A Combined Corner and Edge Detector, Proceedings of the 4th Alvey Vision Conference: pages 147—151, 1988. 

  28. Harris Detector: Steps Find points with large corner response: R > threshold

  29. Harris Detector: Steps Take only the points of local maxima of R

  30. Harris Detector: Steps

  31. Robustness of corner features • What happens to corner features when the image undergoes geometric or photometric transformations?

  32. Intensity scaling:I  aI R R threshold x(image coordinate) x(image coordinate) Affine intensity change I  aI + b • Only derivatives are used, so invariant to intensity shiftI I+b Partially invariant to affine intensity change

  33. Image translation • Derivatives and window function are shift-invariant Corner location is covariantw.r.t. translation

  34. Image rotation Second moment ellipse rotates but its shape (i.e. eigenvalues) remains the same Corner location is covariant w.r.t. rotation

  35. Scaling Corner All points will be classified as edges Corner location is not covariant w.r.t. scaling!

More Related